VERSIL91 commited on
Commit
2bf639e
·
verified ·
1 Parent(s): 4079a99

Training in progress, step 4, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:13a49e651af164c921883424ef0136a2d8da81856834108d561a9a96066a5b54
3
  size 125248064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56338500c30425f1b6cb27e0274b8773fe9c9de1e8e71cde2a740a31f0981ac8
3
  size 125248064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:01dabbd36be7469a2688d5a896db5cbb112e06afd3dd7b1c08339a07fb8fca73
3
  size 64219860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11e58a98af2f188b3887d3fb0502880cb534604c6e4ef277db2353ad89518049
3
  size 64219860
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae4827348f9cd7070f23c7fb42f20924501b2299235a40f565cafb0882c98b0e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f07a6b76bf9c5f4bf889b1042df67f890d1b03821222333d3420211875253e54
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:60f8f27a9d76e31d3721bb37f2f4c76e866b8dedf8d4315f175dac906a4a966d
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.003126832128200117,
5
  "eval_steps": 2,
6
- "global_step": 2,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -37,6 +37,28 @@
37
  "eval_samples_per_second": 15.957,
38
  "eval_steps_per_second": 7.979,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 3007893964062720.0,
60
  "train_batch_size": 2,
61
  "trial_name": null,
62
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.006253664256400234,
5
  "eval_steps": 2,
6
+ "global_step": 4,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
37
  "eval_samples_per_second": 15.957,
38
  "eval_steps_per_second": 7.979,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.004690248192300176,
43
+ "grad_norm": 9.09329891204834,
44
+ "learning_rate": 3e-05,
45
+ "loss": 18.3182,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.006253664256400234,
50
+ "grad_norm": 7.477109909057617,
51
+ "learning_rate": 4e-05,
52
+ "loss": 17.3828,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.006253664256400234,
57
+ "eval_loss": 0.9752212166786194,
58
+ "eval_runtime": 64.2806,
59
+ "eval_samples_per_second": 16.77,
60
+ "eval_steps_per_second": 8.385,
61
+ "step": 4
62
  }
63
  ],
64
  "logging_steps": 1,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 6094943032442880.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null